JP2018194541A - Information searching system and method, and information searching program - Google Patents

Abstract

To automatically search for detection algorithm information for acquiring spectral data necessary for determining an object event from a subject.SOLUTION: When searching for detection algorithm information necessary for determining an object event from a photographed subject 10, an information searching system receives input of information on an object event in the subject to be newly determined, refers to three or more steps of first degree of association between object events in the subject stored in an algorithm database 3 and the detection algorithm information, and searches for one or more pieces of detection algorithm information on the basis of the input information on the object event.SELECTED DRAWING: Figure 13

Description

  The present invention provides an information search system suitable for automatically searching for detection algorithm information for acquiring spectrum data necessary for discriminating a target event from a subject and various shooting conditions of a shooting apparatus for shooting the spectrum data. And a method and an information search program.

  2. Description of the Related Art Conventionally, a spectral imaging apparatus has been proposed that discriminates a desired event for a subject by analyzing a captured image of the subject for each wavelength. The spectral imaging device is a high wavelength resolution spectroscopic information (hereinafter referred to as hyperspectral data) capable of performing spectroscopy over several tens of bands with a wavelength resolution of 0.1 nm to 100 nm in the wavelength range from ultraviolet to visible and further to infrared. ) Can be obtained. By utilizing such hyperspectral data, it is possible to analyze, for example, food freshness, building structure defects, plant photosynthesis, chemical elements contained in minerals, moisture and stains on the skin with high accuracy. It becomes. That is, according to the spectrum imaging apparatus, it is possible to detect not only the subject but also the target event in the subject, instead of simply capturing only the subject.

  Examples of spectral imaging devices that can acquire such hyperspectral data are disclosed in Patent Documents 1 and 2, for example.

  Patent Document 1 discloses a spectrum imaging apparatus that uses a tumor site in a human body as a target event. According to the technology disclosed in Patent Document 1, a tumor site and a non-tumor site are identified by performing detection while focusing on the fluorescence wavelength corresponding to the component accumulated in the cancer cell.

  Patent Document 2 discloses an information processing apparatus for determining whether or not a subject is a fruit. A reference feature amount of the fruit is acquired in advance, and it is determined whether or not the subject is a fruit based on a comparison with the feature amount of the spectral image of the actually captured subject. These reference feature amounts are all based on spectrum data.

  In addition, a technique that focuses on image analysis of hyperspectral data is also disclosed (see, for example, Patent Document 3).

International Publication No. 13/002350 JP 2017-3495 A Japanese Patent Laying-Open No. 2015-166682

  However, studying a detection algorithm for acquiring spectrum data necessary for discriminating a target event in this subject requires a lot of time and labor, and also requires technical knowledge.

  For example, the detection algorithm for obtaining the spectrum data of the tumor site in the human body mentioned above pays attention to the fact that protoporphyrin IX accumulated in cancer cells emits fluorescence of 635 nm, and photoprotoporphyrin emits fluorescence of 675 nm. Therefore, a detection algorithm capable of detecting these fluorescences is assembled. In constructing such a detection algorithm, it is necessary to have technical knowledge such as what is the component accumulated in these cancer cells and what wavelength of fluorescence is emitted, and furthermore, only these fluorescence is accurately detected. A lot of time and effort are required for various studies to extract well and identify accurately.

  For this reason, there has been a demand for a technique that can easily acquire an optimal detection algorithm each time new target events of a subject occur one after another. However, Patent Documents 1 to 3 do not specifically disclose a technique for acquiring an optimal detection algorithm according to a target event of a subject.

  Also, development costs can be reduced by automatically searching for conditions for designing an imaging device that actually captures the subject and conditions for photographing the subject (hereinafter collectively referred to as imaging conditions). In addition, although it is necessary to shorten the development period, Patent Documents 1 to 3 do not disclose any technology that can meet such a request.

  Therefore, the present invention has been devised in view of the above-described problems, and the object of the present invention is detection algorithm information for obtaining spectrum data necessary for discriminating a target event from a subject, An object of the present invention is to provide an information search system and method, and an information search program capable of automatically searching for shooting conditions of a shooting device that takes this.

  In order to solve the above-mentioned problems, the inventors input information related to a target event of a subject to be newly determined when searching for detection algorithm information necessary for determining the target event from a photographed subject. 1 or more based on the input information about the target event, referring to the first degree of association of three or more stages of each target event of the subject stored in the first association database and the detection algorithm information. Invented an information search system and method, and an information search program for searching for detection algorithm information.

  An information search system according to the present invention is an information search system that searches for detection algorithm information of spectrum data necessary for discriminating a target event from a photographed subject, and includes three target events of the subject and the detection algorithm information. A first association database in which first and higher degrees of association are stored in advance, target event input means for inputting information on a target event of a subject to be newly determined, and the first association database. Search means for searching for one or more detection algorithm information based on the information related to the target event input through the target event input means with reference to the first association degree is provided.

  An information search system according to the present invention is an information search system for searching for shooting conditions of a shooting device for discriminating a target event from a shot subject, and includes three or more stages of each target event of a subject and each shooting condition. A first association database in which a degree of association is stored in advance; a target event input means for inputting information relating to a target event of a subject to be newly determined; and the first association in which the first association database is stored. And a search means for searching for one or more photographing conditions based on information about the target event input through the target event input means.

  The information search program according to the present invention is an information search program for searching detection algorithm information necessary for determining a target event from a photographed subject, and a target event that receives input of information related to a target event of a subject to be newly determined Referring to the first association degree in three or more stages of the input step, each object event of the subject stored in the first association database, and the detection algorithm information, it relates to the object event input in the object event input step And a search step for searching for one or more detection algorithm information based on the information.

  An information search program according to the present invention is an information search program for searching for shooting conditions of a shooting device for determining a target event from a shot subject. The target event input in the target event input step with reference to the first relevance in three or more stages of the input step, each target event of the subject, and each shooting condition stored in the first link database And a search step for searching for one or more imaging conditions based on the information on the computer.

  The information search method according to the present invention is an information search method for searching detection algorithm information necessary for determining a target event from a photographed subject, and a target event for receiving input of information on a target event of a subject to be newly determined Referring to the first association degree in three or more stages of the input step, each object event of the subject stored in the first association database, and the detection algorithm information, it relates to the object event input in the object event input step And a search step for searching for one or more detection algorithm information based on the information, each step being executed by a computer.

  The information search method according to the present invention is an information search method for searching for shooting conditions of a shooting device for determining a target event from a shot subject. The target event input in the target event input step with reference to the first relevance in three or more stages of the input step, each target event of the subject, and each shooting condition stored in the first link database And a search step for searching for one or more photographing conditions based on the information on the information, and each step is executed by a computer.

  According to the present invention having the above-described configuration, it is possible to easily acquire optimal detection algorithm information of spectrum data corresponding to a target event of a subject to be determined. For this reason, each time new target events of a subject are born one after another, it is possible to reduce the burden of labor for studying an optimal detection algorithm, and to shorten the time.

1 is a block diagram showing an overall configuration of an information search system according to a first embodiment to which the present invention is applied. It is a block diagram of the search device which comprises an information search system. It is a block diagram of the spectrum imaging device which comprises an information search system. It is a figure for demonstrating the detailed structure of the control part in a spectrum imaging device. It is a figure which shows the block structural example of an imaging device. It is a flowchart which shows the processing operation procedure of an information search program. It is a figure for demonstrating the example which discriminate | determines the freshness of a certain fruit via spectrum data. It is a figure which shows the network which linked | related the objective event for a reference of a to-be-photographed object, and detection algorithm information with the 1st relevance degree. It is a figure which shows the example which linked | related the various parameters of these illumination systems and the imaging system with 1st relevance in addition to the objective event of a to-be-photographed object. It is a figure for demonstrating the other example of 1st relevance. It is a figure which shows the network which linked | related the objective event for reference of a to-be-photographed object, and imaging | photography conditions with the 1st correlation. It is a figure which shows the network which linked | related the objective event for reference of a to-be-photographed, reference | standard imaging | photography conditions, and imaging | photography conditions with the 1st relevance. FIG. 6 is a data flow diagram from input of a target event of a subject to acquisition of imaging conditions of the imaging apparatus. It is a block diagram which shows the whole structure of the information search system which concerns on 2nd Embodiment to which this invention is applied. It is a figure which shows the example with which the imaging conditions with respect to the combination of several detection algorithm information etc. were linked | related by the 3rd or more steps of 2nd linkage. It is a figure for demonstrating the other example of 2nd relevance. It is a figure for demonstrating the example of the 2nd association degree of a combination. It is a figure which shows the example which prescribed | regulated the conditions of the filter in the detection algorithm information for a left side, and prescribed | regulated the conditions of the image pick-up element in the imaging | photography condition of the right side. It is a figure which shows the 3rd relevance required in order to discriminate | determine automatically the target event by spectrum data. It is a figure which shows the 3rd degree of 3rd relationship or more with the discrimination | determination result of the target event of the object with respect to a combination. It is a figure which shows the example in which the 4th degree of association of the 3 steps or more with the design information which should be searched is set.

  Hereinafter, an information search system to which the present invention is applied will be described in detail with reference to the drawings.

First Embodiment FIG. 1 is a block diagram showing the overall configuration of an information search system 1 according to a first embodiment to which the present invention is applied. The information search system 1 searches for detection algorithm information to be provided to the spectrum imaging device 4. The information search system 1 is connected to the algorithm database 3, the search device 2 connected to the algorithm database, and the search device 2. A spectral imaging device 4 and an imaging device 5 are provided.

  In the algorithm database 3, a database related to detection algorithm information to be provided to the spectrum imaging device 4 is constructed. In addition, the algorithm database 3 is a database related to shooting conditions of the shooting device 5. The algorithm database 3 stores information sent via a public communication network or information input by a user of this system. The algorithm database 3 transmits the accumulated information to the search device 2 based on a request from the search device 2.

  The search device 2 is composed of electronic devices such as a personal computer (PC), for example. In addition to the PC, the search device 2 is embodied in any other electronic device such as a mobile phone, a smartphone, a tablet terminal, and a wearable terminal. It may be made.

  FIG. 2 shows a specific configuration example of the search device 2. The search device 2 performs wired communication or wireless communication with a control unit 24 for controlling the entire search device 2 and an operation unit 25 for inputting various control commands via operation buttons, a keyboard, and the like. A communication unit 26 for searching, a search unit 27 for searching for optimal detection algorithm information, and a storage unit 28 for storing a program for performing a search to be executed, represented by a hard disk or the like. It is connected. Further, the internal bus 21 is connected to a display unit 23 as a monitor for actually displaying information.

  The control unit 24 is a so-called central control unit for controlling each component mounted in the search device 2 by transmitting a control signal via the internal bus 21. Further, the control unit 24 transmits various control commands via the internal bus 21 in accordance with an operation via the operation unit 25.

  The operation unit 25 is embodied by a keyboard or a touch panel, and an execution command for executing a program is input from the user. When the execution command is input from the user, the operation unit 25 notifies the control unit 24 of this. Upon receiving this notification, the control unit 24 executes a desired processing operation in cooperation with each component including the search unit 27.

  The search unit 27 searches for detection algorithm information of spectrum data necessary for discriminating the target event from the subject imaged by the spectrum imaging device 4. The search unit 27 reads various information stored in the storage unit 28 as necessary information and various information stored in the algorithm database when executing the search operation. The search unit 27 may be controlled by artificial intelligence. This artificial intelligence may be based on any known artificial intelligence technology.

  The display unit 23 includes a graphic controller that creates a display image based on control by the control unit 24. The display unit 23 is realized by, for example, a liquid crystal display (LCD).

  When the storage unit 28 is composed of a hard disk, based on the control by the control unit 24, predetermined information is written to each address and is read out as necessary. The storage unit 28 stores a program for executing the present invention. This program is read by the control unit 24 and executed.

  FIG. 3 shows a configuration example of the spectrum imaging apparatus 4. The spectrum imaging device 4 is configured by a so-called multispectral camera, a camera with a color filter exchange method, or a camera with a prism. The spectrum imaging device 4 captures a subject and further acquires a spectral image therefrom. The spectral imaging device 4 generates a spectral image based on three-dimensional spectral data having two-dimensional spatial information and one-dimensional wavelength information from the two-dimensional spectral data at each photographing position. The spectral image generated by the spectral imaging device 4 is composed of a plurality of two-dimensional images indicating the reflectance or transmittance of the subject for each wavelength. As an example of this spectral image, in a wavelength range of a predetermined wavelength range of 200 nm to 13 μm, a wavelength resolution of 0.1 nm to 100 nm may be used, and a spectral image for each band.

  Incidentally, the wavelength range in the spectral image captured by the spectral imaging device 4 includes not only the visible light region but also light in the infrared region, near infrared region, and ultraviolet region.

  The spectral imaging apparatus 4 includes an objective lens 41 that takes in light emitted by the imaging target itself, light reflected or transmitted by the subject 10, that is, an imaging lens L from the subject 10, and a Y-axis direction in a three-axis orthogonal coordinate system including XYZ. A precision linear motion stage 42 that moves in the direction of Z, a slit plate 43 for disposing a slit opening 43a provided in the Z-axis direction on the image plane of the objective lens 41, and a light beam that has passed through the slit opening 43a as parallel light. A collimating lens 44, a dispersive optical element 45 that disperses parallel light from the collimating lens 44, an imaging lens 46 that captures a light beam emitted from the dispersive optical element 45, and an image surface of the imaging lens 46. Image sensor 47, precision linear motion stage 42 and image sensor 47 are controlled, and each of the image data received through image sensor 47 is also controlled. And a control unit 48 that performs processing. Note that the spectrum imaging device 4 may use the technology disclosed in Japanese Patent Application Laid-Open No. 2015-166682.

  The precision linear motion stage 42 moves the slit plate 43, the collimating lens 44, the dispersion optical element 45, the imaging lens 46, and the imaging element 47 integrally in the Y-axis direction under the control of the control unit 48.

  The dispersion optical element 45 is embodied by a diffraction grating, a prism, or the like, for example. The dispersion optical element has a function of dispersing the light beam passing through the collimating lens 44 into components for each wavelength.

  The image sensor 47 is constituted by, for example, a CCD image sensor, a CMOS image sensor, or the like. The imaging element 47 converts light imaged on the imaging surface into an electric signal by photoelectric conversion. Then, the electrical signal converted by the image sensor 47 is transmitted to the control unit 48. If light in the infrared region, near-infrared region, and ultraviolet region is received, an image sensor 47 suitable for the light is provided.

  FIG. 4 shows a further detailed configuration of the control unit 48. The control unit 48 includes an imaging control unit 481 that controls the timing at which an electric signal is acquired by the image sensor 47, and a movement control unit 482 that controls the movement direction, movement amount, and movement timing of the precision linear motion stage 42 in the Y-axis direction. A spectral data creation unit 483 that creates spectral data based on the electrical signal from the image sensor 47, and an image processing unit 484 that performs various image processing, calibration, and the like based on the spectral data created by the spectral data creation unit 483. And. Note that some or all of the components of the control unit 48 may be mounted in an independent personal computer (PC).

  The spectroscopic data creation unit 483 creates two-dimensional spectroscopic data having one-dimensional spatial information and one-dimensional wavelength information based on the electrical signal transmitted from the image sensor 47, and stores this. The spectral data generation unit 483 repeatedly executes these processes, and when imaging at all imaging positions is completed, obtains a hyperspectral image made up of three-dimensional spectral data having two-dimensional spatial information and one-dimensional wavelength information. It becomes possible.

  The image processing unit 484 converts the spectral image for each wavelength created by the spectral data creation unit 483 into a predetermined color system, performs color calculation processing, and generates a color analysis image. Further, the image processing unit 484 performs processing for displaying the generated color analysis image by a predetermined display method. The image processing unit 484 includes a calibration processing unit 484-1, a calculation unit 484-2, and a color analysis image acquisition unit 484-3.

  The calibration processing unit 484-1 performs noise removal due to dark current, inter-pixel sensitivity deviation correction processing, luminance calibration processing, correction of illumination unevenness of light source light in the space, and the like.

  The calculation unit 484-2 calculates each spectral radiance, each spectral luminance, and the like in the spectral image for each wavelength processed by the calibration processing unit 484-1.

  The color analysis image acquisition unit 484-3 is a standard set by using various parameters calibrated by the calibration processing unit 484-1 and each spectral radiance, each spectral luminance, etc. calculated by the calculation unit 484-2. A color space conversion process is performed for conversion to the color system.

  The color analysis image subjected to the color space conversion processing by the color analysis image acquisition unit 484-3 is sent to a PC or the like (not shown) and drawn on a display or the like.

  FIG. 5 shows a block configuration example of the photographing apparatus 5. The imaging device 5 includes a general digital camera, a multispectral camera, and any digital camera mounted on a mobile phone, a smartphone, a tablet terminal, or a wearable terminal. The spectral imaging device 4 can detect spectral data in all bands, while the imaging device 5 is limited to a predetermined wavelength region in addition to normal visible light imaging. It is intended to detect. The photographing device 5 includes an imaging optical system 51, a filter 52, an image sensor 53, and a signal processing unit 54.

  The imaging optical system 51 has at least one imaging lens 56, collects light from the subject 10, and forms an image on the imaging surface of the imaging element 53.

  The filter 52 is disposed between the subject 10 and the imaging lens 56. The filter 52 is disposed on the path of light that reaches the image sensor 53. The filter 52 is an element having a predetermined spectral transmittance. That is, the filter 52 functions to transmit only light in a preset wavelength region and reflect light in other wavelength regions. The type of the filter 52 is selected according to the wavelength and wavelength width of light that is actually desired to be transmitted. The filter 52 will be described as an example in which the filter 52 is fixedly arranged in advance in the photographing apparatus 5, but is not limited thereto. That is, the filter 52 may be configured to be able to sequentially switch a plurality of filters 52 having different wavelength regions that transmit each other.

  The image sensor 53 is configured by a CCD image sensor, a CMOS image sensor, or the like. The imaging element 53 converts light imaged on the imaging surface into an electrical signal by photoelectric conversion. Then, the electrical signal converted by the image sensor 53 is transmitted to the signal processing unit 54.

  The signal processing unit 54 is a circuit that processes an electrical signal sent from the image sensor 53. The signal processing unit 54 generates a spectrally separated image separated for each wavelength range of light from the subject 10 based on the image acquired by the image sensor 53. The signal processing unit 54 may perform various focus controls based on the acquired electrical signal.

  An operation of the information search system 1 having the above-described configuration in the first embodiment will be described.

  First, the search device 2 searches for detection algorithm information to be provided to the spectral imaging device 4 or the imaging device 5 or detection algorithm information to be provided to the imaging device 5. This search process starts when the user himself / herself inputs a target event of a subject to be newly photographed by the spectral imaging device 4 or the photographing device 5. The subject here is a generic term for objects actually photographed by the spectrum imaging device 4 or the imaging device 5, and the target event is an object to be discriminated through the spectrum imaging device 4 or the imaging device 5. Or mean things. For example, when it is desired to distinguish only salt from a mixture of salt and sugar, the subject is a mixture and the target event is salt. For example, when it is desired to discriminate only oil from a mixture of water and oil, the subject is a mixture and the target event is oil. For example, when it is desired to determine the freshness of sushi, the subject is sushi and the target event is freshness. For example, when it is desired to discriminate a spot on the face, the subject is a face and the target event is a spot. For example, when it is desired to discriminate stomach cancer from the stomach, the subject is the stomach and the target event is stomach cancer.

  The user manually inputs the target event of the subject through the operation unit 25. In this input, text data of a target event of a subject created in an electronic device such as another portable terminal or a PC may be input via the Internet.

  The target event of the subject transmitted or input in this way is stored in the storage unit 28.

  Thus, after the target event of the subject is input, the processing operation by the information search program is actually executed. The processing operation flow of this information search program is shown in FIG.

  The information search program performs wording analysis on the target event of the subject input in step S11 and stored in the storage unit 28. (Step S12). For this wording analysis, any existing text mining technology, data mining technology, language analysis processing technology, or the like may be used.

  Next, this information search program extracts the character string of the target event of the subject to be analyzed from any grammatical structural unit such as word, morpheme, phrase, clause, etc., in any one or more units. . For example, when text data “foot blood vessels” is input as the target event of the subject, character strings such as “foot” and “blood vessels” are extracted, and text data “face moisture” is input. In such a case, a character string such as “face” or “moisture” is extracted. The information search program specifies the subject and the target event from the extracted character string. In the example described above, the subject is “foot” and “face”, and the target events are “blood vessel” and “water”. Normally, since the character string constituting the subject is often before the character string constituting the target event, the subject and the target event are specified from the beginning of the extracted character string.

  Alternatively, there may be cases where the user classifies and inputs “foot” as the subject and “blood vessel” as the target event. In such a case, the input subject and the character string of the target event are accepted as they are.

  Next, the information search program moves to step S13 and searches for detection algorithm information having a high degree of association with the character string extracted in step S12. Before this search is performed, the algorithm database 3 stores a reference target event (hereinafter referred to as a reference target event) and three or more levels of relevance (hereinafter referred to as a first target event) classified into two or more types of detection algorithm information. The degree of association is acquired in advance.

  The detection algorithm information here is an algorithm for detecting spectrum data necessary for determining a target event even if the subject is actually imaged by the spectrum imaging device 4 or the imaging device 5. For example, as shown in FIG. 7, it is known that a certain fruit has a difference in spectral intensity (reflectance) in a wavelength band of 500 nm to 700 nm. That is, when a certain fruit is left to stand at room temperature for 1 day, left to stand at room temperature for 3 days, or left to stand at room temperature for 5 days, the spectrum intensity (reflectance) changes greatly when the spectrum intensity is in the wavelength range of 500 nm to 700 nm. Is known. In such a case, it is possible to determine the freshness of the fruit by creating a spectral image in the wavelength range of 500 nm to 700 nm.

  Any one of the wavelength ranges in which such a target event can be identified is specified as the characteristic wavelength. In the example of FIG. 7, any one of the wavelength ranges from 500 nm to 700 nm is specified as the characteristic wavelength. The characteristic wavelength may be specified by one point or a plurality of characteristic wavelengths. As a method of determining the characteristic wavelength, for example, 600 nm which is the central wavelength in the above wavelength range (500 nm to 700 nm) may be used, or a wavelength at which the difference value of the spectrum intensity between the spectra is the largest. In FIG. 7, it can be seen that a convex peak is formed in each spectrum data at a wavelength of about 650 nm. However, such a singular point may be specified as a characteristic wavelength. This characteristic wavelength may be different for each target event of the subject.

  In addition to this, a characteristic wavelength range centered on this characteristic wavelength is set. The characteristic wavelength range is configured with a predetermined wavelength range set in advance, such as ± 10 nm. For this reason, if the characteristic wavelength is 500 nm and the characteristic wavelength range is ± 10 nm, the range in which spectrum data is actually detected is 495 to 505 nm. This characteristic wavelength range may be different for each target event of the subject.

  In addition to these, the detection algorithm information may include various calculation methods. In such a case, the characteristic wavelength and characteristic wavelength range are set as explanatory variables x1, x2,... Xk, and the objective variable y is obtained by substituting these into the arithmetic expression. That is, the objective variable y obtained by y = f (x1, x2,... Xk) can be detection algorithm information. Similarly, the characteristic wavelength and characteristic wavelength range as the individual explanatory variables x1, x2,.

  The algorithm database 3 stores such characteristic wavelengths, characteristic wavelength ranges, and in some cases, calculation methods and calculation formulas that prescribe them, in association with each other for each reference target event of the subject.

  At this time, the algorithm database 3 may be defined based on three or more levels of first associations between the object reference event of the subject and the detection algorithm information. FIG. 8 shows a network in which the target event for reference of the subject and the detection algorithm information are related to each other by three or more levels of first association. For example, the freshness of the fruit is the first relation when the characteristic wavelength and the characteristic wavelength range as the detection algorithm information are 970 ± 10 nm, and the first relation is 80%, 1170 ± 10 nm, and 880 ± 15 nm. When the calculation method is cluster analysis at three wavelengths of 60%, 547 ± 4 nm, 588 ± 10 nm, and 939 ± 5 nm, the first association degree is 40%, and when the calculation method is 455 ± 12 nm, the first association degree is 20%. It is shown that there is. When the calculation method is linear at three wavelengths of 630 ± 5 nm, 750 ± 10 nm, and 1250 ± 5 nm as the characteristic wavelength and characteristic wavelength range as detection algorithm information, the moisture content of the hair is 80% first relevance, 970 ± It is shown that the first relevance is 20% when the thickness is 10 nm. For stomach cancer, when the characteristic wavelength and characteristic wavelength range as detection algorithm information is 970 ± 10 nm, the first association is 20%, 230 ± 12 nm, 400 ± 5 nm, and the calculation method is K-means. In some cases, the first association degree is 40%, and the first association degree is 80% when the calculation method is cluster analysis at three wavelengths of 547 ± 4 nm, 588 ± 10 nm, and 939 ± 5 nm. . This first association degree may be configured by a so-called neural network.

  The first relevance is selected for determining the target event of the subject, in other words, the compatibility of the detection algorithm information selected for determining the target event of the subject via the spectrum imaging device 4 or the imaging device 5. It shows the accuracy of the detection algorithm information. In the above example, it is shown that the detection algorithm for detecting the freshness of the fruit is most compatible when the detection algorithm is 970 ± 10 nm, and that the discrimination can be performed most effectively and with high accuracy. ing. In the fruit freshness detection, when the compatibility is 2 wavelengths of 1170 ± 10 nm and 880 ± 15 nm, the calculation method is cluster analysis with 3 wavelengths of 547 ± 4 nm, 588 ± 10 nm and 939 ± 5 nm. In some cases, this is shown to follow in the order of 455 ± 12 nm.

  Further, the method of notifying the target event of the subject is not limited to the above. For example, as shown in FIG. 9, when the subject is composed of two or more complexes, they are similarly associated through the first association degree. In the example of FIG. 9, an object is a composite in which a plastic material is sandwiched between glass plates as an object, and a scratch in the plastic material is used as a reference event. This composite may be composed of, for example, a laminate in which a metal and a resin are laminated in a plurality of layers, or may be composed of a mixture mixed with each other such as sugar and salt. Good. Further, it may be a complex body such as a ceramic matrix composite material in which ceramics is used as a base material and whiskers are added as a second layer.

  Furthermore, the foreign object in the composite body which consists of a metal and a foreign material may be used as the reference event. In such an example, one of the complexes is the reference event for reference. Further, the subject may be composed of a composite made of three or more of glass, plastic material, and ceramics, for example. Reference purpose events will be defined for each of these complexes.

  In this way, even when the subject is composed of a complex, the detection algorithm information is associated with this through three or more levels of association. If the subject is composed of a composite of metal and foreign matter, in addition to the characteristic wavelength of the metal, the feature wavelength of the foreign matter and the characteristic wavelength that constitutes the detection algorithm information are taken into account, and the target event for reference is extracted from them. In this case, a suitable condition is examined in advance, and this is linked as the degree of association.

  Further, as an example in which the subject is a composite, the mixed crystal state before and after the martensitic transformation may be used as the subject, and individual phases may be used as the reference event. In addition to this, the subject itself is composed of a single-phase material instead of a composite, but the phase after the change when the single-phase material changes in time series is regarded as a reference event. You may do it.

  After shifting to step S13, the information search program performs an operation of selecting one or more detection algorithm information from the character string constituting the target event of the subject extracted in step S12.

  In selecting the detection algorithm information from the character string constituting the target event of the subject extracted in step S12, refer to the first association degree between the target reference event of the subject and the detection algorithm information shown in FIG. To do. For example, if the target event of the subject extracted in step S12 is “leaf photosynthesis”, 1357 ± 10 nm having a high first association degree with the “leaf photosynthesis” when the first association degree is referred to. Is selected as detection algorithm information. Even when the first relevance is low, the relevance itself is recognized 630 ± 5 nm, 750 ± 10 nm, 1250 ± 5 nm, and the calculation method may be selected as detection algorithm information. Of course, detection algorithm information that is not connected with an arrow may be selected.

  Further, when the target event of the subject extracted in step S12 is “leaf moisture”, such an item does not exist in the reference target event of the subject. In such a case, the calculation method is linear at 1357 ± 10 nm, which is the first association with “photosynthesis of leaves” as a reference event for the subject, and at 630 ± 5 nm, 750 ± 10 nm, and 1250 ± 5 nm. The detection algorithm information that is most suitable for the case where there is a case where the calculation method is linear at 630 ± 5 nm, 750 ± 10 nm, 1250 ± 5 nm, and 970 ± 10 nm, which have the first degree of association with “moisture of hair” May be estimated. In that case, for example, 630 ± 5 nm, which is the first degree of association common to each other, may be estimated as detection algorithm information of “moisture of leaf”, or “photosynthesis of leaf”, “moisture of hair” Among them, all those having a first association degree of 40% or more may be estimated as detection algorithm information. In addition, for all detection algorithms having “photosynthesis of leaves”, “moisture of hair” and the first association degree exceeding 0%, the wavelengths weighted and averaged by the respective first association degrees are estimated as detection algorithm information. It may be.

  If the target event of the subject extracted in step S12 is “tongue cancer”, there is no such item in the reference target event of the subject. Regarding “cancer”, “stomach cancer” exists as a target event of the past subject, but “tongue” does not exist as a reference event for the subject. In such a case, estimation may be made based on the past detection algorithm information of “stomach cancer”, or if there is past detection algorithm information about the “lips” or the like of the part close to the “tongue” May be estimated with reference to it.

  Furthermore, when the subject extracted in step S12 is a mixture of sugar and salt, and the extracted target event is salt, the detection algorithm information when the first association shown in FIG. The case where the wavelength is 230 ± 12 nm and 400 ± 5 nm and the calculation method is K-mens is preferentially selected.

  Also, if the subject extracted in step S12 is, for example, “paper” and the extracted target event is “foreign matter”, the subject that matches this even in the light of the first association shown in FIGS. However, the “foreign matter” as the reference event is present when the subject is a mixture of “metal” and “foreign matter”. In such a case, the subject may be a mixture of “metal” and “foreign matter”, and detection algorithm information having a low first association degree when the reference target event is “foreign matter” may be selected. .

  That is, the selection of the detection algorithm information is not limited to the case where the first association degree is selected in descending order, but is selected in the order of the first association degree from the lowest according to the case. Alternatively, any other priority order may be selected.

  Note that the selection method of the detection algorithm information for the target event of the subject extracted in step S12 is not limited to the above-described method, and may be executed based on any method that refers to the first association degree. It may be. Further, the search operation in step S13 may be performed using artificial intelligence. In such a case, the first association degree may be regarded as a neural network.

  Next, the process proceeds to step S14, and the selected detection algorithm information is displayed via the display unit 23. Thus, the user can immediately grasp the detection algorithm information corresponding to the target event of the subject to be determined by visually recognizing the display unit 23.

  The user sets the detection algorithm of the image processing unit 484 in the spectrum imaging device 4 or sets the detection algorithm of the imaging device 5 based on the output detection algorithm information. The detection algorithm is set by performing color calculation processing (hereinafter, characteristic wavelength calculation) based on the characteristic wavelength in addition to the characteristic wavelength and characteristic wavelength range. For example, when the target event of the subject is “leaf photosynthesis” and 1357 ± 10 nm is selected as the detection algorithm, the characteristic wavelength calculation for displaying red is performed for pixels included in the wavelength range, For the pixels not included in the wavelength, the spectral imaging device 4 and the imaging device 5 are set so as to perform a characteristic wavelength calculation for displaying white.

  As a result, the spectral image capturing device 4 or the image capturing device 5 captures the “leaf” as the subject, thereby detecting the spectral data necessary for determining “photosynthesis” as the target event, and using this as the color analysis image. Can be displayed.

  In particular, according to the present invention, it is possible to easily acquire optimal detection algorithm information of spectrum data according to the target event of the subject to be determined by the spectrum imaging device 4 or the imaging device 5. Each time new target events of a subject are born one after another, the burden of labor for studying the optimal detection algorithm can be reduced, and the time can be shortened.

  In addition, the information search system 1 to which the present invention is applied is characterized in that the optimum detection algorithm information is searched through the first association degree set in three or more stages. The first degree of association can be described by a numerical value of 0 to 100%, for example, but is not limited to this, and may be configured at any stage as long as it can be described by a numerical value of three or more levels. Good.

  By searching based on the first relevance expressed by numerical values of three or more levels, search and display in order of the first relevance in a situation where a plurality of detection algorithm information is selected. Is also possible. Thus, if it can be displayed to the user in the order of the first degree of association, it can be urged to preferentially select detection algorithm information with higher possibility. On the other hand, even detection algorithm information with a low first degree of association can be displayed in the sense of a second opinion, and can be useful when analysis cannot be performed well with the first opinion.

  In addition, according to the present invention, it is possible to make a determination without overlooking detection algorithm information that is extremely low, such as 1% of the first relevance. Even if the detection algorithm information has a very low degree of first association, it is connected as a small sign, and it may be useful as detection algorithm information tens or hundreds of times. You can call attention.

  Furthermore, according to the present invention, there is an advantage that a search policy can be determined in a manner of setting a threshold by performing a search based on the first relevance of three or more stages. If the threshold value is lowered, even if the first relevance is 1%, it can be picked up without omission, but on the other hand, a lot of detection algorithm information with a low possibility of suitably detecting the target event of the subject is picked up. In some cases. On the other hand, if the threshold value is increased, only detection algorithm information that is highly likely to be able to suitably detect the target event of the subject can be narrowed down, but detection algorithm information that displays a suitable solution once every tens or hundreds of times. May be overlooked. It is possible to decide which to place importance on the basis of the idea on the user side and the system side, but it is possible to increase the degree of freedom in selecting points to place such emphasis.

  Furthermore, in the present invention, the first association degree described above may be updated. That is, the target event for reference of the subject as shown in FIG. 8 and the detection algorithm information are updated as needed. This update may reflect information provided via a public communication network such as the Internet. When new knowledge about the relationship between the target event for reference of the subject and the detection algorithm information is discovered through site information or writing that can be acquired from the public communication network, the first degree of association is determined according to the knowledge. Is raised or lowered. For example, when a detection algorithm having a certain degree of first association with a target event for a certain subject can be detected with high accuracy through many sites on the public communication network, it is set between them. The first degree of association is further increased. In addition, when there are many cases where a detection algorithm having a certain degree of first association with a target event for a certain subject cannot be detected with high accuracy through a site on the public communication network, it is set between them. The first relevance level is decreased. In addition, when a target event for reference of a subject is detected through a site on the public communication network that it can be detected with high accuracy by an unprecedented detection algorithm, a new first association degree is newly established between them. You may make it update by setting.

  The update of the first degree of association is performed by the system side or the user side based on the contents of research data, papers, conference presentations, newspaper articles, books, etc. by experts other than based on information obtainable from the public communication network. It may be updated artificially or automatically. Artificial intelligence may be used in these update processes.

  The first embodiment is not limited to the above-described embodiment. In addition to the target event of the subject, information to be input is input in the above-described illumination light information, various imaging system parameters, and hardware parameter step S11, and this detection algorithm information is searched. May be.

  The search device 2 may search for shooting conditions to be provided to the shooting device 5. The information search program searches for an imaging condition having a high degree of association with the acquired target event. Prior to performing this search, the algorithm database 3 obtains in advance the first association between the reference event and the shooting conditions as shown in FIG.

  The imaging conditions referred to here are information on illumination light including the wavelength, illumination angle, brightness, conditions of a polarization filter provided in the illumination light, and spectrum imaging at the time of imaging by the spectrum imaging device 4 or the imaging device 5. F value of the device 4 and the photographing device 5 itself, lens NA, focal length, model used, wavelength resolution, spatial resolution, sensitivity to each spectral wavelength, exposure time, autofocus time, shutter speed, shutter method, white balance, Various imaging system parameters such as black balance and gain, and hardware parameters are also included. As the detection algorithm information, in addition to the above-described characteristic wavelength, characteristic wavelength range, and calculation method, the above-described parameters may be added. Each parameter described above may be defined as one condition for obtaining the above-described characteristic wavelength or characteristic wavelength range.

  When associating these various shooting conditions via the first relevance, if the wavelength resolution is assumed, ranking is made into several types such as 96-120 dpi, 120-144 dpi, 144-192 dpi. The first association degree may be associated with each rank.

  For example, as shown in FIG. 10, such a photographing condition includes “white balance OO”, a combination of “lens arrangement P” and “filter W”, “filter Q”, “filter R” and “illumination light”. A combination of “angle OO °”, a combination of “filter S” and “spatial resolution 133-140 dpi”, “exposure time XX ns or more”, “exposure time XX ns”, or the like is set.

  This photographing condition may be composed of a combination of a plurality of factors, or may be composed of a single factor. Also, the same shooting condition of “exposure time” is classified into “exposure time of OOns or more” and “exposure time of less than OOns”, and the second association degree is associated with each. Good. The “filter Q” has a filter transmission wavelength of 600 to 650 nm, for example, the “filter R” has a filter transmission wavelength of 340 to 400 nm, for example, and the “filter S” has a filter transmission wavelength of, for example, Detailed conditions such as 1000 to 1100 nm are assigned.

  The object reference event of the subject and the imaging condition are associated with each other through the first degree of association. For example, “filter Q” is associated with “fruit freshness” at a first association degree of 80%, and “white balance OO” is associated with a first association degree of 20%. “Hair moisture” is associated with the combination of “filter S” and “spatial resolution 133-140 dpi” with a first association degree of 100%, and with respect to the combination of “lens arrangement P” and “filter W”. The first association is 40%. “Leaf photosynthesis” is associated with “white balance OO” with a first association degree of 60%, and with “less than exposure time OOns” with a first association degree of 20%. “Stomach cancer” is associated with the combination of “lens arrangement P” and “filter W” with a first association degree of 80%, and the first association with “filter S” and “spatial resolution 133-140 dpi”. Associated with a degree of 40%. “Glass defect” is associated with “filter R, illumination light angle OO °” with a first association degree of 100%, and “exposure time of OOns or more” with a first association degree of 20%. Associated.

  This first relevance is the compatibility of the photographing conditions in the photographing apparatus 5 in making a determination based on each reference purpose event. In other words, the reference purpose event, and thus the object purpose to be determined by this This shows the accuracy of the design and imaging method in the imaging device 5 for the event. In the above example, the combination of “lens arrangement P” and “filter W” is the most compatible as the imaging condition for “stomach cancer”, so that the most effective and highly accurate discrimination is possible. It has been shown to be. The imaging conditions for “stomach cancer” are shown to be followed by “filter S” and “spatial resolution 133-140 dpi”.

  In the algorithm database 3, the above-described reference event is stored in association with each other through the first association degree for each of these imaging conditions.

  The information search program may refer to the first relevance shown in FIG. 10 when searching for imaging conditions highly compatible with the newly input target event. For example, when the newly input target event is “hair moisture”, when the first association degree is referred to, the reference detection algorithm information corresponding to the first association degree and the “filter” having the first association degree are high. “S” and “Spatial resolution 133-140 dpi” are selected as shooting conditions. A combination of “lens arrangement P” and “filter W” that has a low first relevance but is slightly recognized may be selected as a photographing condition. Similarly, when the newly input target event is “stomach cancer”, a combination of “lens arrangement P” and “filter W” is selected.

  Similarly, in the embodiment shown in FIG. 10, the selection of the shooting condition is not limited to the case where the first association degree is selected in order from the first association degree, and the first association degree is low depending on the case. The items may be selected in order, or may be selected in any other priority order.

  FIG. 11 shows an example in which the reference objective event and the shooting conditions for the combination of the reference shooting conditions are associated with each other by three or more levels of first association. The reference shooting conditions are configured by the same items as the above-described shooting conditions. The first association shown in FIG. 11 is an example in the case where a part of the imaging condition is input as known information in addition to the target event via the operation unit 25. In other words, the target event and part of the shooting conditions are already determined, but the remaining shooting conditions cannot be determined.

  As shown in FIG. 11, reference purpose events and reference imaging conditions are arranged on the left side through the first association degree, and imaging conditions to be actually searched are arranged on the right side through the first association degree. Yes.

  When the reference target event is “fruit freshness” and the reference photographing condition is “filter S”, the node of these combinations has “white balance OO” having a first association degree of 70% and “exposure” "Time xx ns or more" is assumed to be 40% of the first relevance. When the reference shooting condition is “filter S”, “shutter speed XX seconds”, and the reference target event is “leaf photosynthesis”, the node of these combinations is “white balance XX”. The first association degree is 60%, and the “exposure time less than OOns” is the first association degree 40%.

  In the case where such a first association degree is stored in advance, when a known target event and an imaging condition are input via the operation unit 25, the imaging condition is referred to by referring to the first association degree. Can be explored. For example, when “glass defect” is input as the target event via the operation unit 25 and “illumination light angle OO °” is input as the imaging condition, the combination node and association degree are defined. "Lens arrangement", "Filter S, Spatial resolution 133-140 dpi", etc. are selected as appropriate.

  After completing these selections, the information search program displays the selected shooting conditions via the display unit 23 of the search device 2. As a result, the user can immediately grasp the imaging conditions corresponding to the detection algorithm information by visually recognizing the display unit 23. Artificial intelligence may also be used for the shooting condition search operation. That is, the first association degree may be configured by a neural network.

  The user designs the imaging optical system 51, the filter 52, the imaging element 53, the signal processing unit 54, and the like in the imaging device 5 based on the output imaging conditions, or sets the illumination light conditions. Alternatively, various conditions regarding photographing are determined. In addition, the user designs each component of the spectrum imaging device 4 or determines each condition based on the output photographing condition.

  Incidentally, in the process of inputting the known photographing conditions, in addition to the input via the operation unit 25, for example, the known photographing conditions may be automatically extracted. The means for extracting the photographing conditions includes, for example, a device that reads and analyzes electronic data of manuals related to the photographing devices 4 and 5 to be used and information posted on the Internet through a text mining technique. Alternatively, it may be embodied by a PC or the like. Information relating to the shooting conditions may be extracted from the analyzed information and input as the above-described known shooting conditions. As long as the exposure time is extracted as a known photographing condition, a device for measuring the actual exposure time by the photographing devices 4 and 5 may be used, or the photographing devices 4 and 5 may be directly connected to the PC. It is also possible to read the set exposure time.

  FIG. 12 shows an example in which the detection algorithm information for the combination of the reference purpose event and the reference shooting condition, or the combination of the detection algorithm information and the shooting condition is associated with the first association degree of three or more stages. The first association shown in FIG. 12 is an example in the case where a part of the imaging condition is input as known information in addition to the target event via the operation unit 25. That is, although the target event and a part of the shooting conditions have already been determined, the remaining shooting conditions and detection algorithm information cannot be determined.

  As shown in FIG. 12, the reference event and the reference photographing condition are arranged on the left side through the first association degree, and the detection algorithm information or photographing to be actually searched is arranged on the right side through the first association degree. Combinations of conditions and algorithm information are arranged.

  When the reference target event is “fruit freshness” and the reference shooting condition is “illumination light angle of 30 to 60 °”, the node of these combinations is “630 ± 5 nm, image sensor T, illumination The angle of light “OO °” is 60% for the first association, and “970 ± 10 nm, 900 ± 5 nm, cluster analysis” is the first association 40%. When the target event for reference is “leaf photosynthesis” and the reference imaging condition is “spatial resolution is 120 angle of illumination light 30-60 °”, the node of these combinations is “275 ± 12 nm, filter “R” is the first association degree 80%, and “1357 ± 10 nm” is the first association degree 20%.

  In the case where such a first association degree is stored in advance, when a known target event and an imaging condition are input via the operation unit 25, the imaging condition is referred to by referring to the first association degree. Can be explored. For example, when the target event input via the operation unit 25 is “fruit freshness” and the input imaging condition is “illumination light angle 30 to 60 °”, the combination of the nodes and the associations thereof is associated. “630 ± 5 nm, imaging element T, angle of illumination light OO °”, “970 ± 10 nm, 900 ± 5 nm, cluster analysis”, etc., in which the degree is defined, are appropriately selected.

  FIG. 13 shows a data flow from input of a target event of a subject to acquisition of shooting conditions of the shooting device 5.

  The input information includes the target event of the subject, the wavelength of the illumination light that is the illumination system parameter, the illumination angle of the illumination light that illuminates the subject, the brightness of the illumination light, and the spectrum that is the imaging system parameter. These are the wavelength range, wavelength resolution, spatial resolution, spectral wavelength sensitivity, polarization filter, and the like of the imaging device 4 and the imaging device 5. In addition to this, hardware parameters may also be input. Based on the input information, the detection algorithm information including the characteristic wavelength and the characteristic wavelength range and the photographing condition are searched by referring to the first association degree described above. The detection algorithm information obtained in this way refers to past data stored in the algorithm database 3 based on illumination system parameters and imaging system parameters in addition to the input object event of interest. Then, algorithm information and photographing conditions that are most suitable for photographing the subject by the spectral imaging device 4 and the photographing device 5 are selected.

  It is possible to obtain a color analysis image after the calculation by imaging the subject with the spectral imaging device 4 or the imaging device 5 in which the detection algorithm information is set and performing the characteristic wavelength calculation.

  In addition, 1st Embodiment mentioned above is not limited to the aspect mentioned above. Under the premise that the first association degree described above is acquired, in step S11, instead of receiving an input of a target event of a subject, an input of detection algorithm information may be received. In step S13, by referring to the first association degree based on the detection algorithm information that has received this input, the object event of the subject is searched reversely. That is, the relationship between the input and the output in FIGS. 8 and 9 is replaced with the above-described mode, the input is the detection algorithm information, and the output is the target event of the subject.

  As an application example of this aspect, for example, when an unknown subject is imaged by the spectral imaging device 4 or the imaging device 5 and the characteristic wavelengths are 310 nm and 660 nm, the salt in the mixture is the target event of the subject. It is possible to determine that there is a high possibility.

Second Embodiment FIG. 14 is a block diagram showing the overall configuration of an information search system 1 ′ according to a second embodiment to which the present invention is applied. The information search system 1 ′ searches for a shooting condition of the shooting device 5 for discriminating a target event from the shot subject 10. The algorithm database 3, the shooting condition database 6, the algorithm database 3, and the shooting conditions are searched for. A search device 2 connected to the database 6 and a spectrum imaging device 4 and an imaging device 5 connected to the search device 2 are provided.

  In the second embodiment, the same components and members as those in the first embodiment described above are denoted by the same reference numerals, and the description thereof will be omitted.

  The shooting condition database 6 is a database related to shooting conditions of the shooting device 5. The photographing condition database 6 stores information sent via a public communication network or information input by a user of this system. The imaging condition database 6 transmits the accumulated information to the search device 2 based on a request from the search device 2.

  An operation of the information search system 1 having the above-described configuration in the second embodiment will be described.

  First, the search device 2 searches for imaging conditions to be provided to the imaging device 5. This search process starts from obtaining detection algorithm information to be photographed by the photographing device 5. As the detection algorithm information, the detection algorithm information searched through the first embodiment may be applied as it is, or the user may newly input the detection algorithm information. The detection algorithm information acquired in this way is temporarily stored in the storage unit 28.

  In the second embodiment, the information search program searches for imaging conditions having a high degree of association with the acquired detection algorithm information. Before this search is performed, the shooting condition database 6 acquires in advance the degree of association between the detection algorithm information for reference and the shooting conditions as shown in FIG.

  The imaging conditions here indicate a detailed configuration of the imaging optical system 51 in the imaging apparatus 5, a detailed configuration of the filter 52, a detailed configuration of the image sensor 53, and a detailed configuration of the signal processing unit 54. It is. For example, as shown in FIG. 15, the photographing conditions include “white balance OO”, a combination of “lens arrangement P” and “filter W”, “filter Q”, “filter R”, and “illumination light angle ◯”. A combination of “°”, a combination of “filter S” and “spatial resolution 133-140 dpi”, “exposure time of OOns or more”, “exposure time of less than OOns”, and the like are set.

  This photographing condition may be composed of a combination of a plurality of factors, or may be composed of a single factor. Also, the same shooting condition of “exposure time” is classified into “exposure time of OOns or more” and “exposure time of less than OOns”, and the second association degree is associated with each. Good. The “filter Q” has a filter transmission wavelength of 600 to 650 nm, for example, the “filter R” has a filter transmission wavelength of 340 to 400 nm, for example, and the “filter S” has a filter transmission wavelength of, for example, Detailed conditions such as 1000 to 1100 nm are assigned.

  The detection algorithm information is the same as that in the first embodiment described above. That is, the detection algorithm information includes a characteristic wavelength, a characteristic wavelength range, a calculation method, and the like. In addition to the detection algorithm information, the second association degree may be defined by a combination of illumination conditions, various imaging system parameters, hardware parameters, and other known imaging conditions. . Hereinafter, the detection algorithm information associated through the second association degree is referred to as reference detection algorithm information, and the known photographing condition associated through the second association degree is referred to as a reference photographing condition.

  Such reference detection algorithm information and reference shooting conditions and the shooting conditions to be searched are associated with each other through the second association degree. For example, “Filter Q” is associated with a second association degree of 80% for a combination of calculation methods including wavelengths 880 ± 5 nm, 970 ± 10 nm and cluster analysis, and the second association degree for “White Balance OO”. Associated with 20%. A combination of wavelengths 230 ± 12 nm and 630 ± 5 nm is associated with a combination of “filter S” and “spatial resolution 133-140 dpi” with a second association degree of 100%, and “lens arrangement P” and “filter W”. Are associated with a second association degree of 40%. The combination of the wavelength 547 ± 4 nm, the wavelength 275 ± 12 nm, the PLS regression and the shutter speed XX seconds is related to the “white balance OO” with the second association 60%, and the “exposure time less than XX ns” On the other hand, the second association degree is 20%. The combination of the image sensor T and the shutter speed XX seconds is associated with the combination of the “lens arrangement P” and the “filter W” with a second association degree of 80%, and “filter S” and “spatial resolution 133-140 dpi” Are associated with a second association degree of 40%. The characteristic wavelength 455 ± 12 nm is associated with “filter R” at a second association degree of 100%, and is associated with “exposure time OOns or more” at a second association degree of 20%.

  This second degree of association is the compatibility of the photographing conditions in the photographing apparatus 5 when making a determination based on each reference detection algorithm information and reference photographing conditions, in other words, the reference detection algorithm information and the reference This shows the accuracy of the design and the photographing method in the photographing apparatus 5 with respect to the photographing conditions for the subject, and consequently the target event of the subject determined by this. In the above-described example, the combination of “lens arrangement P” and “filter W” is the most compatible as a photographing condition to be searched for the combination of the image sensor T and the shutter speed OO seconds, and is most effective. It is shown that discrimination can be performed with high accuracy. It is shown that “filter S” and “spatial resolution 133-140 dpi” follow this as imaging conditions for the combination of the image sensor T and shutter speed OO seconds.

  In the imaging condition database 6, the above-described reference detection algorithm information and reference imaging conditions are stored in association with each other via the second association degree for each of these imaging conditions.

  The information search program searches for the detection algorithm information and reference imaging conditions searched through the first embodiment, or the imaging conditions that are compatible with the newly input detection algorithm information and reference imaging conditions. You may make it refer to the 2nd relevance degree shown. For example, when the newly input detection algorithm information is a combination of 230 ± 12 nm and 630 ± 5 nm, the reference detection algorithm corresponding to the second association degree or the reference imaging condition described above is referred to. “Filter S” and “Spatial resolution 133-140 dpi” having the second highest degree of association with the information are selected as imaging conditions. A combination of the “lens arrangement P” and the “filter W”, which has a low second association degree but is slightly recognized, may be selected as an imaging condition. Similarly, when the detection algorithm information and the reference shooting condition searched through the first embodiment are the image sensor T and the shutter speed OO seconds, the combination of “lens arrangement P” and “filter W” is selected. It will be.

  Similarly, in the second embodiment, the selection of the shooting condition is not limited to the case where the second association degree is selected in order from the highest second association degree, and the second association degree is low depending on the case. May be selected in order, or may be selected in any other priority order.

  In addition, when the detection algorithm information searched through the first embodiment (input detection algorithm information) does not match the reference detection algorithm information, the characteristic wavelength range of the reference detection algorithm information may be expanded. . For example, when the wavelength of the acquired detection algorithm information is 660 nm, it is not included in any reference detection algorithm information stored in the imaging condition database 6. In such a case, the characteristic wavelength region of the reference detection algorithm information may be extended to ± 30 nm. Alternatively, a similar reference detection algorithm may be assigned by analogy.

  FIG. 16 shows an example in which shooting conditions for a combination of a plurality of reference detection algorithms and reference shooting conditions are associated with each other by three or more second relevance levels. When the detection algorithm for reference and the shooting condition for reference are the combination group of 1) and further the combination group of 2), the second association degree of “white balance OO” is 80% for the combination. The second association degree of the combination of “filter R” and “illumination light angle OO °” is 20%. When the reference detection algorithm is composed of logical products or logical sums of the combination groups of 3) to 5), the combination of “filter S” and “spatial resolution 133-140 dpi” is the second combination. An association degree of 60% and “exposure time less than OOns” is a second association degree of 20%.

  When the second association degree is stored in advance, the detection algorithm information searched through the first embodiment and the known shooting conditions (input detection algorithm information and reference shooting conditions) are 1), 2). In the case of a combination between the combination groups, “white balance ○○” having a second association degree of 80% and “filter R” having a second association degree of 20% are referred to by referring to the second association degree. It becomes possible to search for “illumination light angle OO °”.

  After completing these selections, the information search program displays the selected shooting conditions via the display unit 23 of the search device 2. Thus, the user can immediately grasp the shooting conditions to be searched according to the detection algorithm information and the known shooting conditions by visually recognizing the display unit 23. Artificial intelligence may also be used for the search operation in the second embodiment. That is, the second association degree may be configured by a neural network.

  Incidentally, the second association degree of this combination may be set in the form shown in FIG. In the example of FIG. 17, as the reference detection algorithm information, the second relevance of three or more stages of the shooting conditions to be searched for a combination of one or more reference detection algorithm information and one or more reference shooting conditions. Is set.

  As shown in FIG. 17, the second association degree indicates that a set of combinations of one or more reference detection algorithm information and one or more reference photographing conditions is expressed as so-called hidden layer nodes 61 a to 61 e. Become. In each of the nodes 61a to 61e, reference detection algorithm information, a weight for the reference photographing condition, and a weight for the output solution are set. This weighting is the second degree of association of three or more levels. For example, in the node 61a, “880 ± 5 nm, 970 ± 10 nm, cluster analysis” is the second association degree 80% as the reference detection algorithm information, and “camera spectral characteristic R1” as the reference imaging condition is the second association. It is linked at 80%. In the node 61c, “230 ± 12 nm, 630 ± 5 nm” as the reference detection algorithm information has a second association degree of 60%, and “imaging element T, shutter speed OO seconds” as the reference imaging condition has the second association. The “camera spectral characteristic R2” as the reference photographing condition is associated with the second association degree of 40%.

  When such second association is stored in advance, detection algorithm information searched through the first embodiment and known shooting conditions (input detection algorithm information and reference shooting conditions) are reference detection algorithm information. As “880 ± 5 nm, 970 ± 10 nm, cluster analysis”, and when the reference photographing condition is “shutter speed XX seconds”, the node 61b is associated through the second association degree. In the node 61b, “filter R, illumination angle OO °” is associated with a second association degree of 60%, and “less than exposure time OOns” is associated with a second association degree of 40%. These may be output as search solutions.

  Each of the second association degree connected to the imaging condition to be searched from the node 61 and the second association degree connected to the node 61 from the reference detection algorithm information and the reference imaging condition is configured in three or more stages. However, in other words, the second association degree connected to the imaging condition to be searched from the node 61 and the reference association algorithm information or the second association degree connected to the node 61 from the reference imaging condition are expressed in two stages. You may make it comprise by whether it is connected.

  Similarly, for the first relevance described above, the relevance of the combination is determined on the input side (for example, the reference detection algorithm information in FIG. 17 and the reference photographing condition side) and on the output side (for example, You may connect with the node 61 provided between the side with the imaging | photography conditions which should be searched in FIG. Then, three or more first associations may be set independently from the input side to the node 61 and from the node 61 to the output side, respectively, or may be updated independently.

  The user designs the imaging optical system 51, the filter 52, the imaging element 53, the signal processing unit 54, and the like in the imaging device 5 based on the output imaging conditions, or sets the illumination light conditions. Or various conditions relating to photographing will be determined. In particular, according to the present invention, it is possible to reduce the burden of labor for examining the optimum photographing conditions for the photographing device 5 each time a new target object event is born one after another, and every time new detection algorithm information is generated. Can be shortened.

  In addition, the information search system 1 to which the present invention is applied is characterized in that an optimum photographing condition is searched through the second association degree set in three or more stages. The second association degree can be described by a numerical value of 0 to 100%, for example, but is not limited to this, and may be configured at any stage as long as it can be described by a numerical value of three or more levels. Good.

  By searching based on the second relevance expressed by numerical values of three or more levels, it is possible to search and display in descending order of the second relevance in a situation where a plurality of shooting conditions are selected. It becomes possible. As described above, if the second association degree can be displayed to the user in the descending order, it is possible to prompt the user to preferentially select a more likely shooting condition. On the other hand, even in a shooting condition with a low second association degree, it can be displayed in the sense of a second opinion, and can be useful when it cannot be designed well with the first opinion.

  In addition to this, according to the present invention, it is possible to determine an extremely low photographing condition such as 1% of the second relevance without overlooking. Even if the shooting conditions are very low in the second relationship, it is connected as a slight sign and alerts the user that it may be useful as shooting conditions tens or hundreds of times. can do.

  Furthermore, according to the present invention, there is an advantage that a search policy can be determined in a manner of setting a threshold by performing a search based on the second relevance of three or more stages. If the threshold value is lowered, it is possible to pick up without omission even if the above-mentioned association degree is 1%, but the possibility that it is possible to suitably detect the shooting conditions corresponding to the detection algorithm information and the known shooting conditions is reduced. There is also a case. On the other hand, if the threshold value is increased, the shooting conditions that match the detection algorithm information and known shooting conditions can be narrowed down with high probability, but on the other hand, overlooking shooting conditions that find suitable conditions once every tens or hundreds of times. There is also a case. It is possible to decide which to place importance on the basis of the idea on the user side and the system side, but it is possible to increase the degree of freedom in selecting points to place such emphasis.

  FIG. 18 shows an example in which a filter condition is defined in the left reference imaging condition, and an imaging element condition is defined in the right imaging condition to be searched. In the example of FIG. 15 described above, the imaging element condition is defined in the reference imaging condition on the left side, and the filter condition is defined in the imaging condition to be searched on the right side. is there.

  In the example of FIG. 18, there are imaging elements T, U, and W as imaging conditions to be searched from now on, and the filter conditions are determined to be the filter S or the filter R before the search, so these are for reference on the left side. It is included in the shooting conditions. An optimal image sensor for a certain filter S condition can be searched for through the second association degree shown in FIG.

  As described above, in the second embodiment, among the illumination light information, various imaging system parameters, and hardware parameters, the imaging conditions to be actually searched for and the predetermined conditions are classified in advance. Thus, the second association degree can be formed. As a result, even when the shooting condition to be searched changes every time, the search can be realized by creating in advance the second association degree where the shooting condition to be actually searched is located on the right side.

  Furthermore, in the present invention, the second association degree described above may be updated. That is, the reference detection algorithm information and reference imaging conditions as shown in FIG. 15 and the design information are updated as needed. This update may reflect information provided via a public communication network such as the Internet. When new knowledge about the relationship between design information and reference detection algorithm information and reference shooting conditions is obtained through site information or writing that can be obtained from the public communication network, Increase or decrease the degree. For example, if there are many cases where shooting conditions having a certain degree of association with certain detection algorithm information are very compatible with each other through sites on the public communication network, the second association set between them is set. Increase the degree further. In addition, if there are many cases where shooting conditions having a certain degree of second relevance with respect to certain detection algorithm information are not very compatible with each other through sites on the public communication network, the second set between them. Decrease the two associations. In addition, when it is stated that a certain detection algorithm information can be detected with high accuracy under unprecedented shooting conditions through a site on the public communication network, a new second association degree should be set between them. You may make it update with.

  The update of the second association is not based on information that can be obtained from the public communication network, but the system side or the user side is artificially or automatically based on the research data, papers, and conference presentations by experts. You may make it update to. Artificial intelligence may be used in these update processes.

  In addition, according to this invention, you may make it perform 2nd Embodiment continuously from 1st Embodiment. In such a case, in the first embodiment, first, the target event of the subject is input and the first association degree is referred to, so that the optimum detection algorithm information and photographing conditions corresponding to this are selected. Next, by referring to the second association degree from the selected detection algorithm information and shooting conditions, the optimal shooting conditions of the shooting device 5 corresponding to the second association degree are selected. That is, when a target event of a subject is input, an optimal shooting condition for shooting this by the shooting device 5 is displayed as a solution by the search device 2.

  The data flow of the second embodiment will be described based on FIG. Various imaging conditions of the imaging device 5 are determined based on the detection algorithm information and the imaging conditions searched in the first embodiment. As this imaging condition, any one or more of the above-described imaging optical system 51, filter 52, imaging element 53, hardware parameters such as the signal processing unit 54, imaging system parameters, and illumination light information are included. Is determined. The imaging device 5 in which these imaging conditions are reflected has a preferable configuration for detecting a target event of a subject to be detected based on detection algorithm information. Then, the subject is photographed by the photographing device 5 and the characteristic wavelength calculation is performed, so that a color analysis image after the calculation can be obtained.

  In the second embodiment, in particular, in the case where the photographing apparatus 5 is embodied as any digital camera mounted on a mobile phone, a smartphone, a tablet terminal, or a wearable terminal, in order to obtain a color analysis image thereof. The filter conditions and the filter calculation method of the application software may be included in the shooting conditions. The filter condition in this application software is a condition for determining on the software what specific wavelength and characteristic wavelength range of imaging light are to be transmitted. Similarly, the filter calculation is to determine on the software what specific wavelength calculation is to be performed.

  In the present invention, the target event can be automatically determined based on the spectrum data obtained by photographing the subject by the spectrum imaging device 4 or the imaging device 5 based on the searched detection algorithm information and the imaging conditions. it can. When this determination is performed, the search device 2 may have an automatic determination function.

  FIG. 19 shows the third relevance necessary for automatically determining the target event based on the spectrum data. In this third association example, the spectral data obtained by photographing the subject with the spectral imaging device 4 or the photographing device 5 and the determination result of the target event are learned in advance.

  The algorithm database 3 stores in advance three or more levels of third relations between the spectrum data r1, r2, r3,... And the determination result of the target event as an output solution. According to the example of FIG. 19, when the spectral data is r1, in the defect rate of defects generated on the surface of the glass, the “defect rate 3%” is the third association degree 80% and the “defect rate 4%”. Is set at a third relevance of 60%. Further, when the spectrum data is r2, the “defect rate 5%” is set to 90% and the “defect rate 2%” is set to 40%.

  These third association degrees are the spectral data r1, r2, r3,... Obtained when the subject was previously photographed by the spectral imaging device 4 or the photographing device 5, and the defect rate as the discrimination result in the algorithm database 3. May be stored in advance and set based on them. This third association degree may be configured by a so-called neural network. This third degree of association indicates the accuracy with which to determine the determination result (for example, the above-described defect rate) for actually determining the target event of the subject based on the spectrum data. For example, for the spectrum data r3, “defect rate 1%” with an association degree of 70% is close to the most accurate determination, and “defect rate 3%” with an association degree of 50% is the subsequent accurate determination. . Similarly, with respect to the spectrum data r2, “defect rate 5%” with an association degree of 90% is close to the most accurate determination, and “defect rate 2%” with an association degree of 40% is the subsequent accurate determination. Become.

  Next, spectrum data is newly acquired by actually imaging the glass as a subject with the spectrum imaging device 4 or the imaging device 5 based on the searched algorithm. Based on the acquired spectrum data, an operation of discriminating a target event of the subject is performed. In this determination, the third association degree shown in FIG. 19 acquired in advance is referred to. When the newly acquired spectrum data is the spectrum data r1 or approximate to the spectrum data r1, when referring to the third association degree described above, the “defect rate 3%” having the highest third association degree is obtained. Select as the optimal solution. However, it is not essential to select the most relevant solution with the third degree of association as the optimum solution, and select “4% defect rate” as the optimum solution, although the third degree of association is low but the association itself is recognized. Also good. Of course, an output solution that is not connected with an arrow may be selected. That is, the selection of the determination result of the target event of the subject is not limited to the case where the third association degree is selected in order from the highest third association degree, but is selected in the order from the lowest third association degree according to the case. May be selected, or may be selected in any other priority order.

  In addition, in the case where the obtained spectrum data is partially similar to r2 but partially similar to r3, and it is not known to which one it should be assigned, for example, pay attention to features between images. You may make it judge. In such a case, for example, the brightness of the obtained spectrum data may be regarded as a feature region in the image and may be determined. For example, deep learning or the like may be used to determine which of the obtained spectral data images is similar to r1 to r3. Based on the feature amount on the image through deep learning, it is determined which of r1 to r3 is assigned. In this way, after assigning the obtained spectrum data to any one of r1 to r3, the determination result of the target event of the subject as the output solution is selected on the basis of the third association degree set to these. Become.

  Note that the method for selecting the determination result of the target event of the subject with respect to the obtained spectrum data is not limited to the method described above, and any method can be used as long as it refers to the third association degree. It may be. These search operations may be performed using artificial intelligence.

  FIG. 20 shows three or more stages of the combination of the reference spectrum data r1, r2,..., The detection algorithm information for reference and / or the reference imaging condition, and the determination result of the target event of the subject for the combination. This shows an example in which the third degree of association is set.

  In such a case, as shown in FIG. 20, the third association degree is a set of combinations of reference spectrum data r1, r2,..., Reference detection algorithm information and / or reference imaging conditions. It is expressed as so-called hidden layer nodes 61a to 61e. Each of the nodes 61a to 61e is set with weights for reference spectrum data r1, r2,..., Reference detection algorithm information and / or reference shooting conditions, and a determination result of a target event of a subject. Has been. This weighting is the third degree of association of three or more levels. For example, in the node 61a, the spectrum data r1 is associated with the third association degree of 80%, and “230 ± 12 nm, 630 ± 5 nm” as the algorithm information is associated with the third association degree of 80%. Further, the node 61c has a spectrum data r2 having a third association degree of 60%, “filter S, spatial resolution” as a reference imaging condition is a third association degree of 60%, and “455 ± 12 nm as reference detection algorithm information”. Are linked with a third degree of association of 40%.

  Similarly, when the third degree of association is set, when the spectrum data is newly acquired and the imaging condition and / or the detection algorithm information is newly acquired, the third degree of association is referred to. Then, the discrimination result of the target event of the subject is searched. When the newly acquired spectrum data is r1 and the photographing condition is “white balance OO”, the node 61b is associated through the third association degree. "Is associated with a third degree of association of 60% and" Defect rate of 1% "with a third degree of association of 40%. Based on the third degree of relevance, the determination result of the target event of the subject is selected.

  The present invention may be embodied as a design information search system. In this design information search system, design information for designing a target event is searched based on the determination result of the target event. This design information search may refer to, for example, the fourth relevance described below.

  The design information of the target event here includes all information necessary for designing the target event in the future. For example, when the determination result of the target event is that the moisture content of the face is 70%, information necessary for designing a foundation suitable for this is searched. Or when the discrimination | determination result of a target event is the defect rate of glass, the information required for the material design of glass will be newly searched. As an example of information necessary for this material design, the material P is formed in the first layer, the material Q is formed in the second layer, the dispersion reinforcing fiber is combined, and the material R is further formed in the third layer. It may be like advice that it should be formed.

  In FIG. 21, four or more levels of fourth relations between the reference spectrum data r1, r2,... And the design information to be searched for the combination of the reference target event determination results are set. An example is shown.

  In this case, as shown in FIG. 21, the fourth association degree is a so-called hidden layer node in which a set of combinations of reference spectrum data r1, r2,... It will be expressed as 61a-61e. In each of the nodes 61a to 61e, weights for reference spectrum data r1, r2,..., Reference target event discrimination results, and design information to be searched are set. This weighting is the fourth degree of association of three or more levels. For example, in the node 61a, the spectrum data r1 is associated with the third association degree 80%, and “A component: B component = 1: 3” is associated with the fourth association degree 80% as the discrimination result of the target event. In addition, the node 61c has a spectrum data r2 having a fourth association degree of 60%, “A component: B component = 2: 1” as a discrimination result of the target event is a fourth linkage degree of 60%, and a discrimination result of the target event is “A component: B component = 1: 6” is associated with a fourth association degree of 40%.

  Similarly, when such a fourth degree of association is set, spectrum data is newly acquired, and when the determination result of the target event is newly obtained, the design information is referred to by referring to the fourth degree of association. Explore. When the newly acquired spectrum data is r1 and the discrimination result of the target event is “A component: B component = 5: 1”, the node 61b is associated through the fourth association degree. In 61b, “design information E” is associated with a fourth association degree of 60%, and “design information G” is associated with a fourth association degree of 40%. Design information is selected based on the fourth degree of association.

  Note that the target event determination result may be selected through the third degree of association, or a newly input one may be used.

  In the determination using the third association degree and the fourth association degree, the position information on the position where the subject 10 is imaged, the map information acquired by comparing the position information with the map of the current location, and the subject 10 The determination may be made by combining any one or more of the form information (shape, pattern, color, texture, etc.). In such a case, a position information acquisition unit (not shown) that acquires current position information in real time based on a satellite positioning signal sent from an artificial satellite, a map in Japan, and map information made up of maps of countries around the world are stored. A map information acquisition unit (not shown) is provided separately. The acquisition of form information is configured by a camera that captures an image of the subject 10. It is possible to identify the form (shape, pattern, color, texture, etc.) of the subject 10 from the image of the subject 10 captured by the camera. One or more of the detected position information, map information, and form information is acquired, and a learned model is constructed through the third association degree and the fourth association degree as described above. In such a case, at least one of the position information, the map information, and the form information is arranged on the left side of the node 61 in the third association degree in FIG. 20 and the left side of the node 61 in the fourth association degree in FIG. , It will link to the node 61. That is, the third association degree and the fourth association degree are models that can be determined by combining one or more of position information, map information, and form information. Accordingly, any one or more of the position information, the map information, and the form information can be further combined, and various determinations can be performed through the third association degree and the fourth association degree.

  Note that the form information may include so-called spatial feature information. The spatial feature information here includes spatial position (arrangement) and form (shape, size, pattern, texture, color, texture, etc.). This spatial feature information is a concept including a feature amount on an image used in so-called deep learning technology, and is information for identifying a spatial position (arrangement) and form by extracting the feature amount. This spatial feature information may include a spectral feature amount extracted for each spectrum in addition to a general spatial feature amount. Alternatively, the spatial feature information may be configured by a fusion of the spatial feature amount and the spectral feature amount. Since this spectral feature value is used to extract a feature value based on a spectral image, only a desired subject can be easily separated from the background movement, etc., and the feature value can be extracted. It can be easily performed.

  Further, both the third association degree and the fourth association degree may be configured by artificial intelligence represented by a neural network or the like.

DESCRIPTION OF SYMBOLS 1 Information search system 2 Search apparatus 3 Algorithm database 4 Spectrum imaging device 5 Imaging device 6 Imaging condition database 10 Subject 21 Internal bus 23 Display part 24 Control part 25 Operation part 26 Communication part 27 Search part 28 Storage part 41 Objective lens 42 Precision direct Moving stage 43 Slit plate 43a Slit opening 44 Collimating lens 45 Dispersion optical element 46 Imaging lens 47 Imaging element 47 Control unit 51 Imaging optical system 52 Filter 53 Imaging element 54 Signal processing unit 481 Imaging control unit 482 Movement control unit 483 Spectroscopy Data creation unit 484 Image processing unit 484-1 Calibration processing unit 484-2 Calculation unit 484-3 Color analysis image acquisition unit

Claims (23)

In an information search system that searches for detection algorithm information of spectrum data necessary to discriminate a target event from a photographed subject,
A first association database in which first association degrees of three or more levels of each target event of the subject and the detection algorithm information are stored in advance;
A target event input means for inputting information on a target event of a subject to be newly determined;
Search means for searching for one or more detection algorithm information based on information on the target event input through the target event input means with reference to the first association degree stored in the first relation database; An information search system characterized by comprising: The first association database stores in advance three or more levels of first association between each target event and reference shooting condition of the subject and the detection algorithm information,
The target event input means is input with information on the target event of the subject to be newly determined and known shooting conditions,
The search means refers to the first association degree stored in the first association database, and is based on the information about the target event and the known imaging conditions input via the target event input means. The information search system according to claim 1, wherein the search algorithm information is searched. In an information search system for searching shooting conditions of a shooting device for determining a target event from a shot subject,
A first association database that stores in advance three or more levels of first associations between each object event and each imaging condition;
A target event input means for inputting information on a target event of a subject to be newly determined;
Search means for searching for one or more shooting conditions based on information relating to the target event input through the target event input means with reference to the first association degree stored in the first association database An information search system characterized by comprising. The first association database stores in advance three or more stages of first associations of each objective event and reference imaging condition of the subject and each imaging condition,
The target event input means is input with information on the target event of the subject to be newly determined and known shooting conditions,
The search means refers to the first association degree stored in the first association database, and is based on the information about the target event and the known imaging conditions input via the target event input means. The information search system according to claim 3, wherein the imaging condition is searched. A second association database that stores in advance three or more stages of second association between each of the detection algorithm information and imaging conditions to be searched for an imaging device for discriminating a target event from a captured subject;
The search means refers to the second association degree stored in the second association database, and is based on the searched one or more detection algorithm information or one or more newly input detection algorithm information. The information search system according to claim 1, wherein the imaging condition to be searched is searched. The first association database includes the first association of the detection algorithm information including one or more of one or more characteristic wavelengths according to the target event, a characteristic wavelength range thereof, and an arithmetic expression using the characteristic wavelength as an explanatory variable. The information search system according to any one of claims 1 to 5, wherein the degree is stored. The first relational database further includes one or more of information related to illumination for photographing the subject, imaging system parameters for photographing the subject, and hardware parameters for photographing the subject. The information search system according to any one of claims 2 to 4, wherein the first association degree of the photographing condition is stored. The second association database stores in advance the second association degree of three or more shooting conditions to be searched for a combination of a plurality of detection algorithm information,
The search means refers to the second association degree stored in the second association database, and based on the searched plurality of detection algorithm information or newly input plurality of detection algorithm information, The information search system according to claim 5, wherein an imaging condition to be searched is searched for. The second association database stores in advance three or more levels of the second association with the imaging conditions to be searched for the combinations of the detection algorithm information and the reference imaging conditions.
The search means refers to the second association degree stored in the second association database, and searches for one or more pieces of detected algorithm information or one or more newly entered detection algorithm information and known imaging conditions. The information search system according to claim 5, wherein one or more shooting conditions to be searched are searched based on the information regarding. It further comprises a photographing condition extracting means for automatically extracting the known photographing condition,
The information search system according to claim 2 or 4, wherein the target event input means is input with information relating to a known imaging condition extracted by the imaging condition extraction means. Imaging means for photographing a subject based on detection algorithm information searched by the search means in the information search system according to claim 1 or 2,
An imaging system comprising: an objective event discriminating unit that discriminates an objective event based on spectrum data obtained by imaging with the imaging unit. The target event discrimination means further includes a third linkage database in which third linkage degrees of three or more levels of reference spectrum data and a result of discrimination of the target event of the subject are stored in advance.
The target event determination means refers to the third association degree stored in the third association database, and searches for one or more determination results based on spectrum data obtained by photographing with the photographing means. The imaging system according to claim 11, wherein the determination is made based on the above. The target event discriminating means stores in advance three or more stages of third relations between the reference spectrum data and the discrimination result of the target event of the subject with respect to the combination of the reference detection algorithm information and / or the reference photographing condition. A third linked database that is provided,
The target event discriminating means refers to the third association degree stored in the third association database, spectral data obtained by photographing by the photographing means, detection algorithm information constituting the combination, and / or Alternatively, the imaging system according to claim 11, wherein the determination is made by searching for one or more of the determination results based on imaging conditions. 14. A design information search means for searching for design information for designing a target event based on a result of determination of the target event by the target event determination means in any one or more of the imaging systems according to claim 11. Design information search system characterized by A fourth relational database in which a fourth relational degree of three or more stages of the design information for the combination of the reference spectrum data and the determination result of the target event of the subject is further stored;
The design information search means refers to the fourth association degree stored in the fourth association database, determines spectral data obtained by photographing with the photographing means, and discriminates the target event by the target event discriminating means. The design information search system according to claim 14, wherein the determination is made by searching for one or more of the determination results based on the result. 2. The first association database is updated by reflecting a new relationship between a target event of a subject and detection algorithm information by reflecting it in the first association degree. The information search system of any one of 10-10. The second association database is updated by reflecting the relationship between the imaging condition of the imaging device and the detection algorithm information in the second association degree when newly acquired. 5. The information search system according to item 5. In an information search system for searching for a target event of a subject from detection algorithm information of spectrum data,
A first association database in which first association degrees of three or more levels of each target event of the subject and the detection algorithm information are stored in advance;
Algorithm input means for newly detecting detection algorithm information;
Search means for searching for a target event of one or more subjects based on the detection algorithm information inputted through the algorithm input means with reference to the first association degree stored in the first association database. An information search system characterized by comprising. The information search system according to any one of claims 1 to 12, wherein the search means performs the search using artificial intelligence. In an information search program for searching for detection algorithm information necessary for determining a target event from a photographed subject,
An objective event input step for accepting input of information on an objective event of a subject to be newly determined;
Based on the information about the target event input in the target event input step with reference to the first correlation degree of three or more stages of each target event of the subject stored in the first correlation database and the detection algorithm information, An information search program for causing a computer to execute a search step for searching for one or more pieces of detection algorithm information. In an information search program for searching for shooting conditions of a shooting device for determining a target event from a shot subject,
A target event input step in which information on a target event of a subject to be newly determined is input;
Based on the information on the target event input in the target event input step with reference to the first link degree of three or more stages of each target event of the subject and each shooting condition stored in the first link database An information search program that causes a computer to execute a search step for searching for one or more photographing conditions. In an information search method for searching for detection algorithm information necessary for determining a target event from a photographed subject,
An objective event input step for accepting input of information on an objective event of a subject to be newly determined;
Based on the information about the target event input in the target event input step with reference to the first correlation degree of three or more stages of each target event of the subject stored in the first correlation database and the detection algorithm information, A search step for searching for one or more detection algorithm information, and each step is executed by a computer. In an information search method for searching for shooting conditions of a shooting device for determining a target event from a shot subject,
A target event input step in which information on a target event of a subject to be newly determined is input;
Based on the information on the target event input in the target event input step with reference to the first link degree of three or more stages of each target event of the subject and each shooting condition stored in the first link database And a search step for searching for one or more shooting conditions, and each of these steps is executed by a computer.

Images